CN107343145A - A kind of video camera electronic image stabilization method based on robust features point - Google Patents
A kind of video camera electronic image stabilization method based on robust features point Download PDFInfo
- Publication number
- CN107343145A CN107343145A CN201710563618.2A CN201710563618A CN107343145A CN 107343145 A CN107343145 A CN 107343145A CN 201710563618 A CN201710563618 A CN 201710563618A CN 107343145 A CN107343145 A CN 107343145A
- Authority
- CN
- China
- Prior art keywords
- frame image
- motion vector
- image
- point
- robust features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/681—Motion detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/682—Vibration or motion blur correction
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a kind of video camera electronic image stabilization method based on robust features point.Method includes:Estimation of motion vectors and motion compensation.The estimation of motion vectors is to detect robust features point in detection reference frame image and current frame image using FAST algorithms, characteristic point is described ORB algorithms, approximate KNN FLANN algorithms match to characteristic point, RANSAC algorithm removes Mismatching point, least square fitting global motion vector;The motion compensation compensates motion vector of the video sequence current frame image relative to reference frame image using global motion vector parameter and image affine Transform Model.Method therefor of the present invention is simple, processing is time-consuming short, steady as precision is high, simultaneously, preferably resolve " staring " type video camera video sequence jitter problem caused by the unnecessary external interferences such as platform shake, and this method has versatility, the occasions such as video monitoring, military monitoring can be used in.
Description
Technical field
The present invention relates to video camera field of video image processing, can be applied to the video camera that various positions are fixed, such as
Video monitoring, hand-held camera, space flight and aviation monitoring, military monitoring etc., can preferably be applied to " staring " type infrared video phase
In electromechanical sub- image stabilization system.
Background technology
Electronic steady image is always the key content of video camera image capturing system, and video camera is in " staring " observation process
In shake due to platform and external interference cause the video sequence that camera obtains in imaging process with shake or even distort,
Strong influence is generated to scene observation, while also limit high-level visual task, such as special exercise mesh in video
Target detect and track.
The electronic image stabilization method of video camera leaves many difficult points:Existing electronic steady image such as BMA is commonly available to
Only in the case of translational motion vector, and to noise is more sensitive and the sequence of frames of video to being obtained in dynamic scene
Timing easily causes matching error.Although Gray Projection method algorithm speed is than comparatively fast, requiring the half-tone information that image has
Change abundant, otherwise cannot accurately change obvious Gray scale projection curve, cause electronic steady image effect poor.For red
Outer video camera, the noise of video image of acquisition is larger, half-tone information change is not enriched, thus be not suitable for using BMA and
Gray Projection method realizes electronic steady image function.
For problem above, this method uses the video camera electronic image stabilization method based on robust features point, by image
The present frame for obtaining video sequence and the motion vector of reference frame image that robust features point can be more accurate, precision is high,
Sub-pixel can be reached, while suitable for existing the complicated scenes such as translation, rotation, scaling.
The content of the invention
The purpose of the present invention, a kind of realtime electronic image stabilizing method is to provide for, for solving video camera because platform is trembled
Video sequence shake and aberration problems caused by dynamic and external interference.
To achieve the above object, the present invention adopts the following technical scheme that:
1st, this method implements the step of electronic steady image two:Estimation of motion vectors and motion compensation.
2nd, described method for estimating motion vector is as follows, and reference frame image and present frame figure are detected first with FAST algorithms
Robust features point as in, then the robust features point detected is described using ORB algorithms, after feature point description
Characteristic point is matched using approximate KNN FLANN algorithms, recycles the random sampling uniformity based on statistical method to calculate
Method rejects caused Mismatching point pair in matching process, finally brings reference frame and current frame image into using the matching double points of acquisition
In affine Transform Model, one group of overdetermined equation is obtained, the global motion arrow between image sequence is obtained using least square fitting
Amount;
3rd, described motion compensation process is as follows, in the global motion vector parameter and video sequence that are obtained using step 2)
Current frame image and reference frame image between affine Transform Model video sequence motion vector is compensated, obtain stabilization
Video sequence.
It is an advantage of the current invention that efficiently solve many problems left in video camera electronic steady image processing procedure:
Processing speed is slow, it is impossible to accomplishes in real time, image texture unobvious cause steady as low precision, it is impossible to solves rotation etc. be present between image
Problem.Meanwhile this method does not need additional process chip, cost is low, is easy to implement.
Brief description of the drawings
Fig. 1 is detailed implementation figure of the present invention.
Fig. 2 is specific implementation example of the invention surely picture result, and it is surely as preceding video sequence, wherein before figure (1) is surely picture to scheme a
The 6th frame, figure (2) is, surely as the 54th preceding frame, figure (3) is surely as the 102nd preceding frame;B is schemed to be steady as backsight frequency sequence, wherein
(1) is schemed for steady the 6th frame as after, and figure (2) is steady the 54th frame as after, and figure (3) is steady the 102nd frame as after.
Embodiment
With reference to specific embodiment, i.e. the electronic steady image of the infrared video camera of refrigeration mode 288 × 384 present invention is made into
One step describes, and is only illustrated herein with the suitability example of the present invention to explain the present invention, but be not intended as the restriction of the present invention.
The infrared video camera of refrigeration mode 288 × 384 is by 288 × 384 infrared detectors, analog dither platform, data acquisition
System, power supply composition.In a particular embodiment, unintentionally shaken using shaker deck simulation, so as to which output video sequence can be caused
Row shake, solves this problem using the inventive method.Method is as shown in figure 1, by estimation of motion vectors and motion compensation two
Part forms.
First, video camera is observed a certain region with sleep mode, using a certain frame in video sequence as reference
Frame, it is special to robustness in current frame image and reference frame image respectively using FAST and ORB algorithms after being pre-processed to image
Sign point is detected and described, and then characteristic point is matched using approximate KNN FLANN algorithms, recycled based on statistics
The RANSAC algorithm of method rejects caused Mismatching point pair in matching process, finally utilizes the matching double points obtained
Reference frame is brought into in current frame image affine Transform Model, obtaining one group of overdetermined equation, being obtained using least square fitting
Global motion vector between image sequence
Secondly, using the current frame image in obtained global motion vector parameter and video sequence and reference frame image it
Between affine Transform Model video sequence motion vector is compensated, the video sequence stablized.Electronic steady image in this example
Mean error is 0.0687pixel, and speed is 63 frame per second.Steady picture result is as shown in Figure 2.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, according to system of the present invention and in fact
The equal change and modification that applying method is done, should all be included within the scope of the present invention.Therefore, protection model of the invention
Enclose is defined by scope of the claims.
Claims (1)
- A kind of 1. video camera electronic image stabilization method based on robust features point, by 1) estimation of motion vectors and 2) motion compensation 2 steps are formed, it is characterised in that:1), described method for estimating motion vector is as follows, and reference frame image and current frame image are detected first with FAST algorithms In robust features point, then the robust features point detected is described using ORB algorithms, it is sharp after feature point description Characteristic point is matched with approximate KNN FLANN algorithms, recycles the RANSAC algorithm based on statistical method Caused Mismatching point pair in matching process is rejected, finally reference frame is brought into using the matching double points of acquisition and is imitated with current frame image Penetrate in transformation model, obtain one group of overdetermined equation, the global motion vector between image sequence is obtained using least square fitting;2), described motion compensation process is as follows, in the global motion vector parameter and video sequence that are obtained using step 1) Affine Transform Model between current frame image and reference frame image compensates to video sequence motion vector, is stablized Video sequence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710563618.2A CN107343145A (en) | 2017-07-12 | 2017-07-12 | A kind of video camera electronic image stabilization method based on robust features point |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710563618.2A CN107343145A (en) | 2017-07-12 | 2017-07-12 | A kind of video camera electronic image stabilization method based on robust features point |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107343145A true CN107343145A (en) | 2017-11-10 |
Family
ID=60219682
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710563618.2A Pending CN107343145A (en) | 2017-07-12 | 2017-07-12 | A kind of video camera electronic image stabilization method based on robust features point |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107343145A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107968916A (en) * | 2017-12-04 | 2018-04-27 | 国网山东省电力公司电力科学研究院 | A kind of fast video digital image stabilization method suitable for on-fixed scene |
CN108805832A (en) * | 2018-05-29 | 2018-11-13 | 重庆大学 | Improvement Gray Projection digital image stabilization method suitable for tunnel environment characteristic |
CN110619339A (en) * | 2018-06-19 | 2019-12-27 | 北京深鉴智能科技有限公司 | Target detection method and device |
CN113206951A (en) * | 2021-04-13 | 2021-08-03 | 武汉科技大学 | Real-time electronic image stabilization method based on flapping wing flight system |
CN113497886A (en) * | 2020-04-03 | 2021-10-12 | 武汉Tcl集团工业研究院有限公司 | Video processing method, terminal device and computer-readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102231792A (en) * | 2011-06-29 | 2011-11-02 | 南京大学 | Electronic image stabilization method based on characteristic coupling |
CN103700069A (en) * | 2013-12-11 | 2014-04-02 | 武汉工程大学 | ORB (object request broker) operator-based reference-free video smoothness evaluation method |
CN104144282A (en) * | 2014-07-17 | 2014-11-12 | 西北工业大学 | Fast digital image stabilization method applicable to space robot visual system |
CN104506775A (en) * | 2014-12-31 | 2015-04-08 | 深圳先进技术研究院 | Image collection jitter removing method and device based on stereoscopic visual matching |
CN105657432A (en) * | 2016-01-12 | 2016-06-08 | 湖南优象科技有限公司 | Video image stabilizing method for micro unmanned aerial vehicle |
-
2017
- 2017-07-12 CN CN201710563618.2A patent/CN107343145A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102231792A (en) * | 2011-06-29 | 2011-11-02 | 南京大学 | Electronic image stabilization method based on characteristic coupling |
CN103700069A (en) * | 2013-12-11 | 2014-04-02 | 武汉工程大学 | ORB (object request broker) operator-based reference-free video smoothness evaluation method |
CN104144282A (en) * | 2014-07-17 | 2014-11-12 | 西北工业大学 | Fast digital image stabilization method applicable to space robot visual system |
CN104506775A (en) * | 2014-12-31 | 2015-04-08 | 深圳先进技术研究院 | Image collection jitter removing method and device based on stereoscopic visual matching |
CN105657432A (en) * | 2016-01-12 | 2016-06-08 | 湖南优象科技有限公司 | Video image stabilizing method for micro unmanned aerial vehicle |
Non-Patent Citations (4)
Title |
---|
沈秋: "基于仿射模型的无人机视频实时压缩算法", 《电子与信息学报》 * |
牛维: "头盔摄像头视频的稳像算法研究", 《中国优秀硕士学位论文全文数据库》 * |
王培宇: "车载电子稳像***设计", 《中国优秀硕士学位论文全文数据库》 * |
黄文娟: "运动状态下的视频稳像技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107968916A (en) * | 2017-12-04 | 2018-04-27 | 国网山东省电力公司电力科学研究院 | A kind of fast video digital image stabilization method suitable for on-fixed scene |
CN108805832A (en) * | 2018-05-29 | 2018-11-13 | 重庆大学 | Improvement Gray Projection digital image stabilization method suitable for tunnel environment characteristic |
CN108805832B (en) * | 2018-05-29 | 2022-02-08 | 重庆大学 | Improved gray projection image stabilizing method suitable for tunnel environment characteristics |
CN110619339A (en) * | 2018-06-19 | 2019-12-27 | 北京深鉴智能科技有限公司 | Target detection method and device |
CN113497886A (en) * | 2020-04-03 | 2021-10-12 | 武汉Tcl集团工业研究院有限公司 | Video processing method, terminal device and computer-readable storage medium |
CN113497886B (en) * | 2020-04-03 | 2022-11-04 | 武汉Tcl集团工业研究院有限公司 | Video processing method, terminal device and computer-readable storage medium |
CN113206951A (en) * | 2021-04-13 | 2021-08-03 | 武汉科技大学 | Real-time electronic image stabilization method based on flapping wing flight system |
CN113206951B (en) * | 2021-04-13 | 2022-07-05 | 武汉科技大学 | Real-time electronic image stabilization method based on flapping wing flight system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107343145A (en) | A kind of video camera electronic image stabilization method based on robust features point | |
CN107222662A (en) | A kind of electronic image stabilization method based on improved KLT and Kalman filtering | |
US10542208B2 (en) | Systems and methods for synthesizing high resolution images using image deconvolution based on motion and depth information | |
CN107241544B (en) | Video image stabilization method, device and camera shooting terminal | |
EP3216216B1 (en) | Methods and systems for multi-view high-speed motion capture | |
Grundmann et al. | Calibration-free rolling shutter removal | |
Morimoto et al. | Evaluation of image stabilization algorithms | |
US9716832B2 (en) | Apparatus and method for stabilizing image | |
CN106991650B (en) | Image deblurring method and device | |
KR101524548B1 (en) | Apparatus and method for alignment of images | |
Bosco et al. | Digital video stabilization through curve warping techniques | |
WO2019164704A1 (en) | Saturation management for luminance gains in image processing | |
CN106017695B (en) | Adaptive infrared asymmetric correction method based on state estimation | |
WO2017222649A1 (en) | Method and apparatus for rolling shutter compensation | |
CN111539872A (en) | Real-time electronic image stabilization method for video image under random jitter interference | |
CN109661815B (en) | Robust disparity estimation in the presence of significant intensity variations of the camera array | |
US20220377224A1 (en) | Entropy maximization based auto-exposure | |
CN113875219B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
CN106651918B (en) | Foreground extraction method under shaking background | |
Thillainayagi | Video stabilization technique for thermal infrared Aerial surveillance | |
CN116704111A (en) | Image processing method and apparatus | |
TW201320727A (en) | Image processing device, image processing method, and recording medium | |
Vlahović et al. | Deep learning in video stabilization homography estimation | |
Florez et al. | Video stabilization taken with a snake robot | |
Dale et al. | Target tracking, moving target detection, stabilisation and enhancement of airborne video |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171110 |